Pinned Loading

1. MultiHopKG MultiHopKG Public

   Forked from salesforce/MultiHopKG

   Multi-hop knowledge graph reasoning learned via policy gradient with reward shaping and action dropout

   Jupyter Notebook

2. reinforcement-learning reinforcement-learning Public

   强化学习代码, 对应知乎强化学习专栏博客: https://www.zhihu.com/column/c_1820091444070866944

   Python 2

3. rtp-llm rtp-llm Public

   Forked from alibaba/rtp-llm

   RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

   C++

4. samaritan1998.github.io samaritan1998.github.io Public

   HTML

5. multimodel_rag multimodel_rag Public

   colpali文档检索出文档图片+多模态大模型生成回答

   Python 2